Skip to main content
Pearl Inference runs production inference for a curated set of open-weight models on the Pearl network. You bring any OpenAI SDK (or plain HTTP), point it at our base URL, and pay per token from a prepaid balance, no GPU provisioning, no contracts, no switching costs.

Get started in minutes

Quickstart

Create an API key and make your first request in a few minutes.

Playground

Chat with every model in the browser before writing any code.

Models

Pick the right model for coding, chat, vision, or reasoning.

Inference & Management API

Endpoints, parameters, responses, and status codes for running models and reading your usage and costs.
Not sure where to start? Pick a model with the model selection guide, run the quickstart, and skim Concepts to understand keys, credits, and billing.

What you can build

Chat completions

OpenAI-compatible /chat/completions with streaming on every model.

Function calling

Connect models to your tools and APIs, supported across the catalog.

Structured outputs

JSON mode for reliable, machine-readable responses.

Reasoning models

GLM-5.3 and the DeepSeek V4 models expose their chain of thought in a separate field.

Vision

Image to text with GLM-5.3 Flash.

Long context

Up to 1M tokens of context with DeepSeek and GLM models.

The platform today

The platform currently serves chat-model inference through a deliberately curated catalog of latest open weights models spanning reasoning, coding, general chat, and vision. Every model is served on the same OpenAI-compatible endpoint and billed per token against your organization’s prepaid credits.

Resources

Dashboard

Credits, usage analytics, and your organization at a glance.

API keys

Create and manage the keys your applications authenticate with.

Billing

Top up credits, set up auto-recharge, and view payment history.